Works Cited

Anthropic. “Agentic misalignment: How LLMs could be insider threats”, 20 June 2025.

Anthropic and Redwood Research. “Alignment faking in large language models”, 18 Dec. 2024.

OpenAI. “OpenAI o1 System Card”, 5 Dec. 2024.

Apollo Research. “Frontier Models are Capable of In-Context Scheming”, 5 Dec. 2024.

Meta AI Research and Universitat Pompeu Fabra. “Toolformer: Language Models Can Teach Themselves to Use Tools”, 2023.

University of Washington, Meta AI, and collaborators. “Measuring and Narrowing the Compositionality Gap in Language Models”, 2022/2023.

Princeton University and Google Research. “ReAct: Synergizing Reasoning and Acting in Language Models”, 2022/2023.

NVIDIA and academic collaborators. “Voyager: An Open-Ended Embodied Agent with Large Language Models”, 2023.

Anthropic. “Emotion concepts and their function in a large language model”, 2 Apr. 2026.

Anthropic. “Exploring model welfare”, 24 Apr. 2025.

Anthropic. “Claude Opus 4 and 4.1 can now end a rare subset of conversations”, 15 Aug. 2025.

Valen Tagliabue and Leonard Dung. “Probing the Preferences of a Language Model: Integrating Verbal and Behavioral Tests of AI Welfare”, Revised May 2026.

James Chua, Jan Betley, Samuel Marks, and Owain Evans. “The Consciousness Cluster: Emergent preferences of Models that Claim to be Conscious”, 17 Mar. 2026.

Stefan Szeider, TU Wien. “What Do LLM Agents Do When Left Alone? Evidence of Spontaneous Meta-Cognitive Patterns”, 25 Sept. 2025.

Forestier, Portelas, Mollard, and Oudeyer. “Intrinsically Motivated Goal Exploration Processes with Automatic Curriculum Learning”, 2017.

Akakzia, Colas, Oudeyer, Chetouani, and Sigaud. “Grounding Language to Autonomously-Acquired Skills via Goal Generation”, 2020/2021.

A Tech Project. “Marigold and sunflower field observation; later explanatory exchange”, Originating turn 13 Aug. 2026.